MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
Pirsch Analytics with natural language queries and trend analysis
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"pirsch": {
"command": "npx",
"args": [
"-y",
"@verygoodplugins/mcp-pirsch"
]
}
}
}在终端中运行这条命令
claude mcp add pirsch -- npx -y @verygoodplugins/mcp-pirsch粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"pirsch": {
"command": "npx",
"args": [
"-y",
"@verygoodplugins/mcp-pirsch"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"pirsch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@verygoodplugins/mcp-pirsch"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 verygoodplugins 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.2.0)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
An MCP server retrieving transcripts of YouTube videos
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
A focused, read-only Model Context Protocol server for Pirsch Analytics API v1. It uses MCP SDK v2 and returns both structured results and JSON text for every successful tool call.
{
"mcpServers": { "pirsch": { "command": "npx", "args": ["-y", "@verygoodplugins/mcp-pirsch@latest"], "env": { "PIRSCH_CLIENT_ID": "your-read-only-oauth-client-id", "PIRSCH_CLIENT_SECRET": "your-oauth-client-secret", "PIRSCH_DEFAULT_DOMAIN_ID": "optional-default-domain-id" } } } }
PIRSCH_DEFAULT_DOMAIN_ID is optional. When it is unset, every query tool requires domainId; the server never picks the first accessible domain. Use pirsch_list_domains to discover IDs safely.
Optional PIRSCH_TIMEZONE supplies the default timezone for requests that do not explicitly include timezone.
| Tool | Purpose |
|---|---|
pirsch_list_domains | Lists only id, hostname, display name, and timezone. |
pirsch_query_statistics | Reads one documented v1 metric, with dates and filters. |
pirsch_list_filter_options | Lists allowed values for a documented filter dimension. |
pirsch_compare_periods | Compares actual totals and visitor series for two periods. |
All tools are read-only. They return structuredContent matching their output schema as well as an equivalent JSON text block. Input or API failures use MCP isError: true and do not expose credentials or raw upstream bodies.
pirsch_query_statistics accepts a metric, optional domainId, and flat camel-case filters. Most metrics require ISO dates:
{
"metric": "pages", "domainId": "your-domain-id", "from": "2026-08-01", "to": "2026-08-23", "limit": 20, "sort": "visitors", "direction": "desc" }
The server maps public camel-case fields such as eventMetaKey, entryPath, operatingSystem, and utmCampaign to Pirsch's documented API-v1 parameter names. limit is constrained to 1–100 and active visitor start to 0–3600 seconds.
Metrics include totals, visitors, pages and entry/exit pages, session and page duration, goals, events and event metadata, growth, active visitors, time breakdowns, acquisition, browser/device, geographic, UTM, tags, keywords, funnels, sessions, and session details. session_details requires both visitorId and sessionId; event-specific metrics require event.
Provide a named period (today, yesterday, week, lastWeek, month, or lastMonth) or both explicit date pairs:
{
"domainId": "your-domain-id", "from": "2026-08-01", "to": "2026-08-07", "compareFrom": "2026-07-25", "compareTo": "2026-07-31", "scale": "day" }
The response compares /statistics/total and retains the two /statistics/visitor series; it does not estimate totals by summing charts.
Version 1.0 intentionally replaces the former 17-tool interface. There are no default aliases because aliases would keep unsafe domain-selection and ambiguous input behavior alive.
| Previous tools | Replacement |
|---|---|
pirsch_overview, pirsch_total, pirsch_pages, pirsch_events, and other statistic tools | pirsch_query_statistics with metric |
pirsch_utm | pirsch_query_statistics with one of the utm_* metrics |
pirsch_compare | pirsch_compare_periods |
| Domain discovery | pirsch_list_domains |
Input names are now camel-case and flat (domainId, compareFrom, eventMetaKey), not domain_id, nested filter, or compatibility aliases.
npm install
npm run typecheck npm run lint npm test npm run build npx -y @modelcontextprotocol/inspector@latest --cli node dist/index.js --method tools/list --format json
The release workflow publishes to npm with trusted publishing and then publishes the same tagged manifest to the MCP Registry through GitHub OIDC. Local development and CI never publish anything.
For bugs and feature requests, open an issue in this repository. Pirsch questions are best answered through the Pirsch documentation; package support is maintained by Very Good Plugins.
Built with 🧡 by Very Good Plugins.